专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP3336796A1 SIMULATION PROGRAM, SIMULATION METHOD, AND SIMULATION DEVICE 审中-公开
公开(公告)号：EP3336796A1
公开(公告)日：2018-06-20
申请号：EP15901681.5
申请日：2015-08-14
申请人： Fujitsu Limited
发明人： OHORI, Kotaro , ANAI, Hirokazu , TAKAHASHI, Shingo , UTSUMI, Shintaro
IPC分类号： G06Q50/10 , G06Q50/16
CPC分类号： G06F17/5009 , G06Q50/10 , G06Q50/16
摘要： A simulation program (111) according to an embodiment causes a computer (101) to execute a process (S2) of arranging an agent in a virtual space that includes one or a plurality of places where guide information is set, the agent having perception information and behaving according to the perception information in the virtual space. The simulation program further causes the computer to execute a process (S25) of updating the perception information of the agent according to guide information that is provided according to the position of the agent in the virtual space. The simulation program further causes the computer to execute a process (S23) of deteriorating the perception information, degree of the deteriorating being determined on the basis of at least any one of a behavior of the agent and an attribute of the agent.

2. 发明公开

EP3579177A1 SIMULATION PROGRAM, SIMULATION METHOD, AND SIMULATION APPARATUS 审中-公开
公开(公告)号：EP3579177A1
公开(公告)日：2019-12-11
申请号：EP19177483.5
申请日：2019-05-30
申请人： FUJITSU LIMITED
发明人： YAMANE, Shohei , YAMADA, Hiroaki , OHORI, Kotaro , ANAI, Hirokazu , TAKAHASHI, Shingo
IPC分类号： G06Q50/10 , G06Q50/28
摘要： A simulation method is performed by a computer by using an agent disposed in a virtual space. The method includes: controlling the agent so that the agent behaves in the virtual space under influence of each of a plurality of signs disposed in the virtual space; and determining the influence of each of the plurality of signs on the agent in accordance with an attribute relating to a display mode of the sign and an attribute of the agent.

3. 发明公开

EP4047531A1 MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND MACHINE LEARNING DEVICE 审中-公开
公开(公告)号：EP4047531A1
公开(公告)日：2022-08-24
申请号：EP19949449.3
申请日：2019-10-17
申请人： FUJITSU LIMITED
发明人： KATO, Takashi , GOTO, Keisuke , OHORI, Kotaro
IPC分类号： G06N20/00
摘要： Training data is discretized in a way to improve the model accuracy.
With respect to a plurality of training data records in which combinations of data item values of a plurality of data items are individually associated with label information, the data item values are converted based on a criterion per data item into discretized data values. Training processing for training a model that receives the discretized data values as input and performs determination about the label information is performed by using a plurality of training data records obtained by the conversion. From an execution result of the training processing, a plurality of feature data records, each of which differently indicates a combination of two or more data items for the determination among the plurality of data items and a plurality of index values, which indicates importance level of the plurality of feature data records respectively are acquired. At least one of the feature data records is selected based on the index values, and the criterion for the discretization of the data item values is changed based on the at least one of the feature data records selected.

4. 发明公开

EP3211584A1 SIMULATION METHOD, SIMULATION PROGRAM, AND SIMULATION DEVICE 审中-公开
标题翻译：仿真方法，仿真程序和仿真设备
公开(公告)号：EP3211584A1
公开(公告)日：2017-08-30
申请号：EP14904301.0
申请日：2014-10-24
申请人： Fujitsu Limited
发明人： OHORI, Kotaro , ANAI, Hirokazu , TAKAHASHI, Shingo , HACHIYA, Yuki
IPC分类号： G06Q50/10 , G06F19/00
CPC分类号： G06F17/5009 , G06F19/00 , G06Q50/10
摘要： A movement route is formed in accordance with actual conditions of an intruder. A simulation method, for simulating by using a computer a movement of an intruder that has entered a security zone, that causes the computer to execute a process including generating a model of a movement route by referring to a storage unit that stores information related to a movement route included in the security zone, receiving input of a position to which a security guard is deployed from among positions in the model of the movement route, generating an agent of an intruder at one of the positions in the model of the movement route, and forming a movement route of the agent of the intruder in accordance with the position of the security guard in a case when the security guard is included in an identification scope, in which the agent of the intruder identifies the security guard, when a movement of the generated agent of the intruder is simulated.
摘要翻译：根据入侵者的实际情况形成移动路线。一种模拟方法，用于通过使用计算机来模拟已经进入安全区域的入侵者的移动，该方法使计算机执行包括通过参考存储关于a行进路线的信息的存储单元来产生移动路线的模型的过程移动路径中包括的移动路线，从移动路线的模型中的位置中接收安全警卫所部署到的位置的输入，在移动路线的模型中的一个位置处生成入侵者的代理，以及在保安人员被包括在识别范围内的情况下，根据保安人员的位置形成入侵者的代理人的移动路线，在该识别范围中，入侵者的代理人识别保安人员，对入侵者的生成代理进行仿真。

5. 发明公开

EP4404108A1 INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE 审中-公开
公开(公告)号：EP4404108A1
公开(公告)日：2024-07-24
申请号：EP21957500.8
申请日：2021-09-15
申请人： FUJITSU LIMITED
发明人： IWASHITA, Hiroaki , GOTO, Keisuke , OHORI, Kotaro
IPC分类号： G06N20/00 , G06N5/02
CPC分类号： G06N20/00 , G06N5/02
摘要： An information processing apparatus receives a target data set and classifies the target data set into any of multiple classes with a classifier. The information processing apparatus determines whether or not a positive pattern matching the target data set exists by referring to a positive pattern management table. The information processing apparatus determines whether or not a negative pattern matching target data set exists by referring to a negative pattern management table. The information processing apparatus positively evaluates the classification result of the target data set when the positive pattern exists and the negative pattern does not exist. The information processing apparatus outputs a message indicating that the classification result of the target data set is positively evaluated so that the user may refer to the message.

6. 发明公开

EP4191482A1 PREDICTION PROGRAM, PREDICTION METHOD, AND PREDICTION DEVICE 审中-实审
公开(公告)号：EP4191482A1
公开(公告)日：2023-06-07
申请号：EP20947748.8
申请日：2020-07-31
申请人： FUJITSU LIMITED
发明人： SEKI, Yukiko , OHORI, Kotaro
IPC分类号： G06N20/00 , G06Q10/06 , G16H20/00
摘要： A prediction program of an embodiment causes a computer to execute processing of listing, processing of creating, and processing of determining. In the processing of listing, combinations of feature amounts that are correlated with a target label are listed. In the processing of creating, a policy is created for achieving the target label for a prediction target based on a difference between the listed combinations of the feature amounts and a combination of feature amounts of the prediction target. In the processing of determining, appropriateness of the created policy is determined based on performance information indicating past performances.

7. 发明公开

EP3608849A1 SIMULATION PROGRAM, SIMULATION METHOD AND SIMULATION DEVICE 审中-公开
公开(公告)号：EP3608849A1
公开(公告)日：2020-02-12
申请号：EP18780672.4
申请日：2018-03-02
申请人： Fujitsu Limited
发明人： OHORI, Kotaro , YAMANE, Shohei , YAMADA, Hiroaki , TAKAHASHI, Shingo
IPC分类号： G06Q10/04 , G06Q90/00
摘要： A simulation program according to an embodiment causes a computer to arrange agents in a virtual space in which a plurality of guidance displays is set, the agents each having cognitive information and behaving in the virtual space based on the cognitive information. A first range and a second range different from the first range are set for each of the plurality of guidance displays. The simulation program causes the computer to change cognitive information up to a destination of one of the agents, when the one of the agents enters within the first range of one of the guidance displays, and first guidance information corresponding to the first range is related with the destination. In addition, the simulation program causes the computer to change cognitive information not directly related with a destination of one of the agents for the one of the agents, when the one of the agents enters within the second range, and second guidance information corresponding to the second range is related with the destination.

8. 发明公开

EP4318333A1 INFORMATION PRESENTATION PROGRAM, INFORMATION PRESENTATION METHOD, AND INFORMATION PRESENTATION DEVICE 审中-实审
公开(公告)号：EP4318333A1
公开(公告)日：2024-02-07
申请号：EP21934900.8
申请日：2021-03-31
申请人： FUJITSU LIMITED
发明人： KOYANAGI, Yusuke , UEMURA, Kento , OHORI, Kotaro
IPC分类号： G06N20/00
摘要： An information presentation device generates a plurality of training models by executing machine learning that uses training data. The information presentation device generates hierarchical information that represents, in a hierarchical structure, a relationship between hypotheses shared as common and hypotheses regarded as differences for a plurality of hypotheses extracted from each of the plurality of training models and each designated by a combination of one or more explanatory variables.

9. 发明公开

EP4266186A1 INFORMATION PROCESSING PROGRAM, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING DEVICE 无效
公开(公告)号：EP4266186A1
公开(公告)日：2023-10-25
申请号：EP20965935.8
申请日：2020-12-16
申请人： FUJITSU LIMITED
发明人： UEMURA, Kento , KOYANAGI, Yusuke , OHORI, Kotaro
IPC分类号： G06F16/215 , G06F16/2458
摘要： An information processing program for causing a computer to execute processing including: extracting, for a plurality of pieces of combination data each of which is a combination of a plurality of feature amounts that includes an invariable feature amount and a variable feature amount that represent features of a target, combination data to be processed based on the plurality of pieces of combination data according to relation between the respective pieces of combination data; executing causal search processing for the variable feature amount according to the invariable feature amount by using the combination data to be processed; and selecting, based on a result of the causal search processing, a specific variable feature amount that corresponds to the specified invariable feature amount, to present the selected specific variable feature.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式